Intelligent Lesion Selection: A Novel Method for Longitudinal Assessment of Breast Cancer Lung Metastases

Qahqaie M, Zimmer VA, Castaneda Gavina E, Peltonen K, Laaksolilj J, Lähteenmaa J, Heimann T, Maier A, Neumann D (2026)

Publication Language: English

Publication Type: Conference contribution, Original article

Publication year: 2026

Publisher: PMLR

Series: Proceedings of Machine Learning Research

Book Volume: 301

Pages Range: 1342–1355

Conference Proceedings Title: Proceedings of The 8th International Conference on Medical Imaging with Deep Learning

Event location: Salt Lake City, USA US

URI: https://proceedings.mlr.press/v301/qahqaie26a.html

Abstract

Breast cancer, the second most common cancer globally, often metastasizes to the lungs, requiring frequent computed tomography (CT) scans to monitor disease progression. Manual analysis by radiologists is time-consuming and prone to variability, underscoring the need for automated systems to enhance accuracy and efficiency. The goal of such systems is to optimize processes like RECIST score calculation for tumor response assessment. This study presents a pipeline for the automated temporal analysis of breast cancer lung metastases. Existing lung nodule detection and segmentation models were adapted for detecting and segmenting breast cancer metastases. Registration-based lesion tracking was incorporated, and a novel Temporal Lesion Pair Classifier was developed to identify significant lesions and estimate tumor load evolution by summing their diameters, following an adaptation of the RECIST guidelines. Evaluated on a unique dataset of breast cancer patients, each with multiple annotated CT scans at different disease stages, the proposed pipeline demonstrated a 42% reduction in median tumor size progression discrepancy for consecutive study pairs and improved tumor response classification accuracy by 22% at the patient level.

Authors with CRIS profile

Melika Qahqaie Lehrstuhl für Informatik 5 (Mustererkennung) Eduardo Castaneda Gavina Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

APA:

Qahqaie, M., Zimmer, V.A., Castaneda Gavina, E., Peltonen, K., Laaksolilj, J., Lähteenmaa, J.,... Neumann, D. (2026). Intelligent Lesion Selection: A Novel Method for Longitudinal Assessment of Breast Cancer Lung Metastases. In Tolga Tasdizen; Shireen Elhabian; Ronald Summers; Chen Chen; Lisa Koch; Yan Zhuang (Eds.), Proceedings of The 8th International Conference on Medical Imaging with Deep Learning (pp. 1342–1355). Salt Lake City, USA, US: PMLR.

MLA:

Qahqaie, Melika, et al. "Intelligent Lesion Selection: A Novel Method for Longitudinal Assessment of Breast Cancer Lung Metastases." Proceedings of the The 8th International Conference on Medical Imaging with Deep Learning (MIDL 2025), Salt Lake City, USA Ed. Tolga Tasdizen; Shireen Elhabian; Ronald Summers; Chen Chen; Lisa Koch; Yan Zhuang, PMLR, 2026. 1342–1355.

BibTeX: Download